From a28da6ed9a385c8624d45510ad96928b2585cf70 Mon Sep 17 00:00:00 2001 From: Charlotte Koch Date: Sun, 31 Dec 2023 15:03:49 -0800 Subject: Comments in the unicodify script. --- script/unicodify.sed | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/script/unicodify.sed b/script/unicodify.sed index 09e70cf..d0df04b 100644 --- a/script/unicodify.sed +++ b/script/unicodify.sed @@ -1,9 +1,17 @@ +# Remove spaces on either end of an em-dash. s,[[:space:]]--[[:space:]],\&\#8212;,g + +# Explicitly handle double-quotes before single-quotes. s,"`,\&\#8220;,g s,`",\&\#8221;,g s,'`,\&\#8216;,g s,`',\&\#8217;,g + +# Diacritics. s,\ï,\&\#239;,g s,\è,\&\#232;,g s,\é,\&\#233;,g + +# Remove Asciidoc comments now, for the sake of getting more accurate +# wordcounts. s,//.*,,g -- cgit v1.2.3